Machine Learning for Performance Enhancement of Molecular Dynamics Simulations
Machine Learning for Performance Enhancement of Molecular Dynamics Simulations
复制标题
DOI：
10.1007/978-3-030-22741-8_9
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
J. Kadupitiya;G. Fox;V. Jadhao
中科院分区：
文献类型：
--
作者：
J. Kadupitiya;G. Fox;V. Jadhao
我们探索将机器学习与模拟相结合的想法，以提高模拟的性能，并提高其在研究和教育方面的可用性。这个想法是用混合OpenMP/MPI并行分子动力学模拟来说明的，该模拟旨在提取纳米限制下离子的分布。我们发现基于人工神经网络的回归模型成功地学习了与输出离子密度分布相关的所需特征，并快速生成与显式分子动力学模拟结果非常一致的预测。结果表明，利用机器学习可以进一步提高并行计算的性能增益。
We explore the idea of integrating machine learning with simulations to enhance the performance of the simulation and improve its usability for research and education. The idea is illustrated using hybrid OpenMP/MPI parallelized molecular dynamics simulations designed to extract the distribution of ions in nanoconfinement. We find that an artificial neural network based regression model successfully learns the desired features associated with the output ionic density profiles and rapidly generates predictions that are in excellent agreement with the results from explicit molecular dynamics simulations. The results demonstrate that the performance gains of parallel computing can be further enhanced by using machine learning.